Computational intelligence modelling of pharmaceutical tabletting processes using bio-inspired optimization algorithms

In pharmaceutical development, it is very useful to exploit the knowledge of the causal relationship between product quality and critical material attributes (CMA) in developing new formulations and products, and optimizing manufacturing processes. With the big data captured in the pharmaceutical industry, computational intelligence (CI) models could potentially be used to identify critical quality attributes (CQA), CMA and critical process parameters (CPP). The objective of this study was to develop computational intelligence models for pharmaceutical tabletting processes, for which bio-inspired feature selection algorithms were developed and implemented for optimisation while artificial neural network (ANN) was employed to predict the tablet characteristics such as porosity and tensile strength. Various pharmaceutical excipients (MCC PH 101, MCC PH 102, MCC DG, Mannitol Pearlitol 200SD, Lactose, and binary mixtures) were considered. Granules were also produced with dry granulation using roll compaction. The feed powders and granules were then compressed at various compression pressures to produce tablets with different porosities, and the corresponding tensile strengths were measured. For the CI modelling, the efficiency of seven bio-inspired optimization algorithms were explored: grey wolf optimization (GWO), bat optimization (BAT), cuckoo search (CS), flower pollination algorithm (FPA), genetic algorithm (GA), particle swarm optimization (PSO), and social spider optimization (SSO). Two-thirds of the experimental dataset was randomly chosen as the training set, and the remaining was used to validate the model prediction. The model efficiency was evaluated in terms of the average reduction (representing the fraction of selected input variables) and the mean square error (MSE). It was found that the CI models can well predict the tablet characteristics (i.e. porosity and tensile strength). It was also shown that the GWO algorithm was the most accurate in predicting porosity. While the most accurate prediction for the tensile strength was achieved using the SSO algorithm. In terms of the average reduction, the GA algorithm resulted in the highest reduction of inputs (i.e. 60%) for predicting both the porosity and the tensile strength.     

A multi-variate heart disease optimization and recognition framework

Neural Computing and Applications - Cardiovascular diseases (CVD) are the most widely spread diseases all over the world among the common chronic diseases. CVD represents one of the main causes of...     

Fatigue Crack Tip Plasticity for Inclined Cracks

The evaluation of the crack tip deformation is essential to the estimation of crack growth under either static or cyclic loading. A 3-D elastic–plastic finite element analysis was developed to simulate the crack tip deformation along mixed mode inclined edge cracks in a steel plate subjected to either monotonic or cyclic loading at selected R-ratios. In this paper, two types of crack configurations were investigated: inclined cracks with equal inclined lengths (EICL) and inclined cracks with equal horizontal projection length (ECHP). The development of the monotonic (Δm) and cyclic (Δc) crack tip plastically zones and the monotonic (CTOD) and cyclic (ΔCTOD) crack tip opening displacements were traced to find the effect of the crack inclination angle, which significantly affected the size and shape of the crack tip plastic zone. The finite element results compared well with the analytical results based on modified Dugdale’s model. It was observed that Mode II has a significant effect on the plastic zone in the case of equal inclined crack length (EICL), i.e., Mode II increases as the crack angle decreases. Also, it is interesting to note that for the EICL case, the magnitude of Δc is delayed to appear with decreasing the inclination angle, for example, for θ?=?90° the cyclic plastic zone appeared at Δσ?=?103.32 MPa, while for θ?=?45° the cyclic plastic zone appeared at Δσ?=?132.84 MPa. Whereas, the variation of monotonic and cyclic plastic zone size in the equal crack horizontal projection (ECHP) case is not affected by the crack inclination angle. Furthermore, it was observed that the static crack tip opening displacement (CTOD) and the cyclic (ΔCTOD) are independent of the crack inclination angle in case of ECHP, due to such cracks take into consideration the effect of inclination angle through its length.     

A multi-verse optimizer approach for feature selection and optimizing SVM parameters based on a robust system architecture

Neural Computing and Applications - Support vector machine (SVM) is a well-regarded machine learning algorithm widely applied to classification tasks and regression problems. SVM was founded based...     

Performance optimization of integrated gas and power within microgrids using hybrid PSO–PS algorithm

In this paper, a hybrid algorithm consisting of particle swarm optimization and pattern search algorithm is proposed to evaluate and optimize the design and operation of microgrids (MGs) in combined gas and power networks. Key performance indicators (KPIs) are modeled and proposed to evaluate and assess MGs. The paper begins by proposing a comprehensive study to define KPIs, which are used to evaluate the following MG parameters: economical efficiency, reliability, environmental conservation, and power quality. Multi‐objective evaluation functions are then developed by building a relationship matrix of MG and KPI components. The results are then displayed as optimized power generation percentages for each technology with values for four KPI categories: cost, quality, reliability and environmental friendliness. Two case studies are examined in this paper; both the province of Ontario and Toronto regional zone under all system parameters with varying percentage of generation via gas technology. Results indicated that the optimal scenario for both Ontario and Toronto was achieved at hybrid PSO–patern search percentage generation via gas technology with improved cost KPI and other KPIs remaining approximately constant. Copyright © 2016 John Wiley & Sons, Ltd.     

A multi‐objective evolutionary optimization of fuzzy controller for energy conservation in air conditioning systems

This paper presents the use of evolutionary optimization approach to design and tune smart fuzzy controllers for heating, ventilation, and air conditioning systems or HVAC. The objective is to optimize energy consumption while accounting for user comfort requirements. The problem of energy conservation in air conditioning systems becomes a multi‐objective optimization constrained problem, which enlarges the solution search space. To solve this problem, a multi‐objective evolutionary optimization technique based on genetic algorithm (GA) is proposed. A physical experimental setup is constructed for data collection and formulation of mathematical model. A fuzzy controller is initially designed through expert knowledge, and GA is then used to tune the rules and membership functions of the fuzzy controller in order to optimize multiple objectives. Simulations and real experiments are compared to determine the effectiveness of the proposed strategy. As compared to the controller present in the real experimental air conditioner, approximately 15% energy is successfully saved with no increase in average individual dissatisfaction or discomfort index. Also, a decrease in peak individual dissatisfaction or discomfort index from 91% to 62% is observed. Copyright © 2013 John Wiley & Sons, Ltd.     

Precipitation Behavior of Modified as Cast High Nitrogen Super Hard High‐Speed Tool Steel

The properties of high‐speed tool steels can be improved by modifying their chemical composition or the technology of production. Nitrogen alloying is an attractive technology to enhance the mechanical and physical properties of tool steels. In this work, modified super hard high‐speed tool steel was produced through nitrogen alloying and decreasing the level of cobalt content in investigated steels. This work aims to study the effect of nitrogen as alloying element on carbides and carbo‐nitrides precipitates type, shape, and size for investigated steels. From the results obtained from Thermo‐Calc, it was concluded that nitrogen alloying produced large amount of stable austenite, also eutectic carbides precipitates (M₆C and M₇C₃) were stable at room temperature. Transmission electron microscope (TEM) images for traditional grade showed that the as cast structure contains beside the carbides network other single carbides precipitates. While on the other hand the selected area diffraction pattern (SADP) images of nitrogen alloyed grade shows fine carbides and carbo‐nitrides precipitates with more amount of retained austenite in the ferrite matrix, they showed also the presence of the eutectic precipitates as well as the dislocations.     

Impact of the Cd2+ treatment on the electrical properties of Cu2ZnSnSe4 and Cu(In,Ga)Se2 solar cells

The present contribution aims at determining the impact of modifying the properties of the absorber/buffer layer interface on the electrical performance of Cu₂ZnSnSe₄ (CZTSe) thin‐film solar cells, by using a Cd²⁺ partial electrolyte (Cd PE) treatment of the absorber before the buffer layer deposition. In this work, CZTSe/CdS solar cells with and without Cd PE treatment were compared with their respective Cu(In,Ga)Se₂ (CIGSe)/CdS references. The Cd PE treatment was performed in a chemical bath for 7 min at 70 °C using a basic solution of cadmium acetate. X‐ray photoemission spectroscopy measurements have revealed the presence of Cd at the absorber surface after the treatment. The solar cells were characterized using current density–voltage (J–V), external quantum efficiency, and drive‐level capacitance profiling measurements. For the CZTSe‐based devices, the fill factor increased from 57.7% to 64.0% when using the Cd PE treatment, leading to the improvement of the efficiency (η) from 8.3% to 9.0% for the best solar cells. Similar observations were made on the CIGSe solar cell reference. This effect comes from a considerable reduction of the series resistance (R_S) of the dark and light J–V, as determined using the one‐diode model. The crossover effect between dark and light J–V curves is also significantly reduced by Cd PE treatment. Copyright © 2015 John Wiley & Sons, Ltd.